Information processing system

Abstract

Provided is an information processing system that assists in correcting a document by using a language model. A processing unit of the information processing system is configured to execute: processing for extracting at least one component from a first document; processing for creating a first prompt having a first instruction sentence including a command for extracting, from a second document, at least one description corresponding to the component; processing for causing the language model to generate a first response sentence from the first prompt; processing for determining whether or not the description conforms to a regulation; processing for creating a second prompt having a second instruction sentence including a command for presenting a correction plan for conforming the description to the regulation if the description does not conform to the regulation; processing for causing the language model to generate a second response sentence from the second prompt; and processing for generating result data on the basis of the component, the description, and the correction plan.

Description

Information Processing Systems

[0001] TECHNICAL FIELD One aspect of the present invention relates to an information processing system and an information processing method, and more particularly, to an information processing system and an information processing method that can utilize processing using a language model.

[0002] One embodiment of the present invention is not limited to the above technical field, and examples of the technical field of one embodiment of the present invention include semiconductor devices, display devices, light-emitting devices, power storage devices, memory devices, electronic devices, lighting devices, input devices (e.g., touch sensors), input / output devices (e.g., touch panels), driving methods thereof, and manufacturing methods thereof.

[0003] In recent years, the development of language models using neural networks has been actively carried out, and large-scale language models (LLMs) in particular have attracted attention. A large-scale language model is a natural language processing model trained using a large amount of data. A large-scale language model can realize a dialogue model that responds to user instructions, for example. Non-Patent Document 1 discloses GPT-4 (Generative Pre-trained Transformer 4) (registered trademark) as a large-scale language model, and also discloses ChatGPT as a dialogue model.

[0004] The use of large-scale language models has significantly increased the capabilities of natural language processing models. However, as language models become larger, it is difficult to incorporate and operate language models in-house due to the equipment and cost involved. Therefore, one way to use language models is to use external services that provide language models.

[0005] Summary of ChatGPT / GPT-4 Research and Perspective Towards the Future of Large Language Models, Yiheng Liu et al. (Submitted on 4 Apr 2023, [online], Internet <URL: https: / / arxiv.org / abs / 2304.01852>

[0006] Due to recent improvements in the performance of language models, there are more opportunities to use language models when correcting documents. However, correcting documents using a language model requires instructing the language model to make corrections, confirming the corrections, and reflecting them in the document, which is time-consuming. Therefore, while system support is effective, it is necessary to optimize corrections using language models.

[0007] An object of one embodiment of the present invention is to provide an information processing system that supports document correction by utilizing a language model.An object of one embodiment of the present invention is to provide an information processing system that optimizes document correction work by utilizing a language model.An object of one embodiment of the present invention is to provide a highly convenient information processing system.An object of one embodiment of the present invention is to provide a novel information processing system.

[0008] Note that the description of these problems does not preclude the existence of other problems. One embodiment of the present invention does not necessarily have to solve all of these problems. Problems other than these can be extracted from the description in the specification, drawings, and claims.

[0009] One aspect of the present invention is an information processing system including a receiving unit, a processing unit, and an output unit. The receiving unit is configured to receive document data including a first document and a second document, and the processing unit executes the following operations: extracting at least one component from the first document, creating a first prompt having a first instruction sentence including an instruction to extract at least one description corresponding to the component from the second document, causing a language model to generate a first response sentence from the first prompt, determining whether the description conforms to a rule, creating a second prompt having a second instruction sentence including an instruction to suggest a revision to make the description conform to the rule if the description does not conform to the rule, causing the language model to generate a second response sentence from the second prompt, and generating result data based on the component, the description, and the revision suggestion; and the output unit is configured to output the result data.

[0010] Alternatively, in the above information processing system, the description preferably includes at least one specific example corresponding to the component.

[0011] Alternatively, in the above information processing system, the condition for a description to conform to the regulations is that the number of specific examples included in the description reaches a specified number, and if the description does not conform to the regulations, the processing unit is configured to execute a process to create a judgment result including the number of missing specific examples, and it is preferable that the second prompt has the judgment result.

[0012] Alternatively, in the information processing system, the proposed revision preferably includes a description and includes revision examples generated in accordance with the number of specific examples that are lacking based on the determination.

[0013] Alternatively, one aspect of the present invention is an information processing system including a receiving unit, a processing unit, and an output unit. The receiving unit is configured to receive document data including a first document and a second document, the processing unit executes the following steps: extracting at least one component and at least one first numerical constraint corresponding to the component from the first document, creating a first prompt having a first instruction sentence including an instruction to extract at least one second numerical constraint corresponding to the component from the second document, causing a language model to generate a first response sentence from the first prompt, creating a second prompt having a second instruction sentence including an instruction to, if the second numerical constraint does not conform to a specification, present at least one suggested modification to make the second numerical constraint conform to the specification, causing the language model to generate the second response sentence from the second prompt, and generating result data based on the component, the second numerical constraint, and the suggested modification; and the output unit is configured to output the result data.

[0014] Alternatively, in the information processing system, it is preferable that the determination be made as to whether or not the second numerical limit range matches the first numerical limit range.

[0015] Alternatively, in the above information processing system, it is preferable that the first document is a patent claim belonging to a patent application, and the second document is a specification belonging to the patent application.

[0016] According to one aspect of the present invention, an information processing system or an information processing method can be provided that utilizes a language model to support document correction. According to one aspect of the present invention, an information processing system or an information processing method can be provided that optimizes document correction work using a language model. According to one aspect of the present invention, a highly convenient information processing system or an information processing method can be provided. According to one aspect of the present invention, a novel information processing system or an information processing method can be provided.

[0017] Note that the description of these effects does not preclude the existence of other effects. One embodiment of the present invention does not necessarily have all of these effects. Effects other than these can be extracted from the description in the specification, drawings, and claims.

[0018] FIG. 1 is a diagram illustrating an example of an information processing system. FIG. 2 is a diagram illustrating an example of an information processing system. FIG. 3 is a block diagram illustrating an example of an information processing system. FIG. 4 is a diagram illustrating an example of an information processing method. FIG. 5 is a diagram illustrating an example of an information processing method. FIGS. 6A, 6B, 6C, and 6D are diagrams illustrating an example of an information processing method. FIGS. 7A, 7B, 7C, and 7D are diagrams illustrating an example of an information processing method. FIGS. 8A and 8B are diagrams illustrating an example of an information processing method. FIG. 9 is a diagram illustrating an example of an information processing method. FIGS. 10A and 10B are diagrams illustrating an example of an information processing method. FIGS. 11A and 11B are diagrams illustrating an example of an information processing method. FIG. 12 is a diagram illustrating an example of an information processing system. FIG. 13 is a block diagram illustrating an example of an information processing system. FIG. 14 is a diagram illustrating an example of an information processing system. FIG. 15 is a diagram illustrating an example of an information processing system.

[0019] The embodiments will be described in detail with reference to the drawings. However, the present invention is not limited to the following description, and it will be readily understood by those skilled in the art that various changes can be made in form and detail without departing from the spirit and scope of the present invention. Therefore, the present invention should not be interpreted as being limited to the description of the embodiments shown below.

[0020] In the configuration of the invention described below, the same parts or parts having similar functions are denoted by the same reference numerals in different drawings, and repeated explanations thereof will be omitted. Furthermore, when referring to similar functions, the same hatching pattern may be used and no particular reference numeral may be assigned.

[0021] Furthermore, for ease of understanding, the position, size, range, etc. of each component shown in the drawings may not represent the actual position, size, range, etc. Therefore, the disclosed invention is not necessarily limited to the position, size, range, etc. disclosed in the drawings.

[0022] In this specification, the ordinal numbers "first" and "second" are used for convenience and do not limit the number of components or the order of the components (for example, the order of processes or the order of stacking). Furthermore, the ordinal numbers assigned to components in one part of this specification may not match the ordinal numbers assigned to the same components in other parts of this specification or in the claims.

[0023] In this specification, when the same symbol is used for multiple elements, and particularly when it is necessary to distinguish between them, an identification symbol such as “_1”, “[n]”, or “[m, n]” may be added to the symbol.

[0024] Embodiment In this embodiment, an information processing system according to one embodiment of the present invention will be described with reference to FIGS.

[0025] <Configuration Example 1 of Information Processing System> Fig. 1 shows an example of an information processing system according to this embodiment. The information processing system according to this embodiment includes an information processing device 10, an information terminal 20, and an information processing device 40. In the information processing system shown in Fig. 1, the information processing device 10 is connected to the information processing device 40 via a network 30. The information processing device 10 is also connected to a plurality of information terminals 20 via a network 31. Fig. 1 shows information terminals 20a, 20b, 20c, and 20d as examples of the information terminals 20.

[0026] A user of the information processing system can access the information processing device 10 from the information terminals 20a to 20d, etc. The user can then receive a service using the information processing method according to one aspect of the present invention.

[0027] A user can use the information processing device 10, for example, by using dedicated software or an application installed on the information terminal 20. Alternatively, a user can use the information processing device 10, for example, from a web browser on the information terminal 20.

[0028] An organization such as a company that provides a service using an information processing method according to one embodiment of the present invention (hereinafter also referred to as a service provider) can provide the service using the information processing device 10. The service provider does not need to prepare the information processing device 40 on its own, but can use the information processing device 40 via the network 30.

[0029] The information processing device 10 is a device that can execute processing using an information processing method according to one aspect of the present invention. In FIG. 1, a server computer is illustrated as an example.

[0030] The information processing device 10 can perform information processing such as calculations using data input from the information terminal 20a via the network 31. The information processing device 10 can transmit the results of the information processing to the information terminal 20a via the network 31. This can reduce the calculation load on the information terminal 20a. Here, the information terminal 20a has been described as an example, but the same can be said for the information terminals 20b to 20d.

[0031] The information processing device 10 can input data to the information processing device 40 via the network 30. The information processing device 40 can perform information processing such as calculations using the input data. The information processing device 40 can transmit the results of the information processing to the information processing device 10 via the network 30. This can reduce the calculation load on the information processing device 10. The information processing device 10 can then transmit the data received from the information processing device 40 or data created based on the data to the information terminal 20a via the network 31.

[0032] The information terminals 20a to 20d are each an information terminal device such as a computer used by a user, and may also be referred to as a client computer. FIG. 1 illustrates, as an example, the information terminal 20a, which is a desktop computer; the information terminal 20b, which is a notebook computer; the information terminal 20c, which is a smartphone; and the information terminal 20d, which is a tablet computer. The information terminal 20d can also be used as a notebook computer by connecting it to a housing 21 having a keyboard. The number of information terminals connected to the information processing device 10 is not particularly limited. While FIG. 1 shows four information terminals, the number of information terminals may be one, two, three, five, or more. Examples of such information terminals include desktop information terminals, notebook information terminals, tablet information terminals, and mobile information terminals such as smartphones.

[0033] The information terminal 20 is provided with, for example, a display unit. The display unit can display, for example, information indicated by data input to the information terminal 20. This allows the user of the information terminal 20 to recognize the information.

[0034] The display unit of the information terminal 20 may be, for example, a liquid crystal display device, a light-emitting device (for example, a light-emitting device having a light-emitting element such as an organic EL element in each pixel), an electrophoretic display device, a DMD (Digital Micromirror Device), a PDP (Plasma Display Panel), an FED (Field Emission Display), or other display device.

[0035] The information processing device 10 is a large computer such as a server computer or a supercomputer. The information processing device 10 is a computer with higher processing power than the information terminal 20. The information processing device 10 can function as a parallel computer. By using the information processing device 10 as a parallel computer, it is possible to perform large-scale calculations required for learning and inference of artificial intelligence (AI), for example. The information processing device 10 may also be capable of performing processing using a natural language processing model using AI.

[0036] The information processing device 40 is a large computer such as a server computer or a supercomputer. The information processing device 40 is a computer with higher processing power than the information terminal 20. The information processing device 40 is also a computer with higher processing power than the information processing device 10. It is preferable that the information processing device 40 has a function as a parallel computer. By using the information processing device 40 as a parallel computer, it is possible to perform large-scale calculations required for AI learning and inference, for example. Note that when both the information processing device 10 and the information processing device 40 have a function as a parallel computer, the information processing device 40 has a higher processing power and can perform large-scale calculations than the information processing device 10.

[0037] The information processing device 40 can perform processing using a natural language processing model that uses AI. Examples of the natural language processing model that uses AI include BERT (Bidirectional Encoder Representations from Transformers) and T5 (Text-to-Text Transfer Transformer). The information processing device 40 can also perform processing using a model that utilizes a large-scale language model. Examples of large-scale language models include GPT-3, GPT-3.5, GPT-4, LaMDA (Language Model for Dialogue Applications), PaLM (Pathways Language Model), PaLM2, Llama2, and Llama3, and it is preferable to use GPT-4.

[0038] The information processing device 40 can execute processing using a general-purpose AI model that can perform various tasks. When the information processing device 10 and the information processing device 40 can each execute processing using a model that uses a large-scale language model, the information processing device 40 can execute processing using a larger-scale AI model than the information processing device 10.

[0039] Network 31 is a computer network smaller than network 30. Typically, network 30 is a global network, and network 31 is a local network. It is preferable to use the Internet, which is the foundation of the World Wide Web (WWW), as network 30. It is preferable to use an intranet or an extranet as network 31. In this embodiment, an example will be mainly described in which the Internet is used as network 30 and an intranet is used as network 31.

[0040] Other computer networks that can be used as the network 31 include a PAN (Personal Area Network), a LAN (Local Area Network), a CAN (Campus Area Network), a MAN (Metropolitan Area Network), a WAN (Wide Area Network), and a GAN (Global Area Network).

[0041] Furthermore, when wireless communication is performed, communication standards such as the fourth generation mobile communication system (4G), fifth generation mobile communication system (5G), and sixth generation mobile communication system (6G), or specifications standardized by the IEEE such as Wi-Fi (registered trademark) and Bluetooth (registered trademark), can be used as communication protocols or communication technologies.

[0042] Either the network 30 or the network 31 can be applied to transmitting and receiving data between the information terminal 20 and the information processing device 10. Also, either the network 30 or the network 31 can be applied to transmitting and receiving data between the information processing device 10 and the information processing device 40.

[0043] The information processing system shown in FIG. 1 is suitable for a case where a user who uses the information terminal 20 and a service provider belong to the same organization such as a company.

[0044] For example, it is preferable that data is transmitted and received between the information terminal 20 and the information processing device 10 using a network 31 established within an organization such as a company. It is also preferable that data is transmitted and received between the information processing device 10 and the information processing device 40 using the Internet. This allows applications, tools, services, etc. provided outside the organization to be used more safely than when the information terminal 20 is directly connected to the information processing device 40 via the Internet.

[0045] The flow of data in the information processing system shown in Fig. 1 will be described with reference to Fig. 2. In Fig. 2 and other figures, the order of data transmission and reception is indicated by circled numbers.

[0046] First, the user inputs desired data DA1 into the information processing device 10 using the information terminal 20. The data DA1 is transmitted from the information terminal 20 to the information processing device 10 via the network 31a.

[0047] The data DA1 is document data corresponding to the document to be corrected. The format of the data DA1 is not particularly important, but it is preferably text data. Details of the data DA1 will be explained later in <Information Processing Method 1>.

[0048] The documents included in the document data accepted by an information processing system according to an embodiment of the present invention are not particularly limited. The information processing system according to an embodiment of the present invention can support the revision of various types of documents. Examples of such documents include patent applications, utility model registration applications, books, magazines, newspapers, contracts, papers (including academic papers, theses, doctoral dissertations, essays, journal articles, etc.), court decisions, terms and conditions, product manuals, novels, publications, white papers, technical documents, and business documents. More specifically, patent application documents include one or more of the specification, claims, and abstract of a patent application.

[0049] The above-mentioned document data may include a first document and a second document. The first document and the second document may be, for example, documents related to an invention. Specifically, the first document may be a patent claim belonging to a patent application, and the second document may be a specification belonging to the patent application. The first document and the second document may include, for example, components of the invention and descriptions related to the components. The components of the invention are elements that constitute the technical features of the invention. Furthermore, the descriptions related to the components may include, for example, specific examples or numerical limitations. The numerical limitations are matters that specify the invention, quantitatively expressed by a numerical range.

[0050] In this specification, an invention is a technical idea that utilizes the laws of nature. In this specification, the composition of an invention includes, for example, each of the constituent elements (also known as technical elements) of the invention and the connection between multiple constituent elements. In addition, the means for solving a problem, or part of such means, can also be called the composition of an invention.

[0051] When the data DA1 includes data other than text data, it is preferable to convert the data DA1 into text data in the information processing device 10. When converting various data into text data, it is preferable to use AI technology. The following describes an example in which the data DA1 is text data. Note that when the data DA1 includes data other than text data, the data DA1 can be read as text data generated using the data DA1.

[0052] The information processing device 10 preferably has a function of generating text data using image data. For example, the information processing device 10 can generate text data using image data by performing processing using at least one AI technology such as image recognition, handwritten character recognition, and caption generation. The information processing device 10 may also have an optical character recognition (OCR) function.

[0053] Next, the information processing device 10 creates data DA2 based on the data DA1. The data DA2 is a prompt that the user inputs to the language model. For example, text data can be used for the data DA2. The prompt corresponds to an input sentence that causes the language model to perform a desired operation. When a prompt is given, the language model generates a response content based on the prompt. Details of the data DA2 will be described later in <Information Processing Method 1>.

[0054] The information processing device 10 can create data DA2 by adding second text data to first text data. Here, the first text data is part of the text data included in data DA1, and the second text data is text data corresponding to an instruction sentence in a prompt to be input to a language model. Here, the instruction sentence is part of the prompt to be input to a language model, and can be rephrased as a question sentence, an imperative sentence, or the like.

[0055] The second text data may be a system prompt. In this specification, a system prompt refers to an instruction in a prompt that is preset by a developer or a service provider. Presetting a system prompt makes it easier to obtain a desired answer from a language model.

[0056] An example of the second text data is an instruction sentence including a command to correct a sentence, such as "Please correct target sentence A." Note that the text data included in target sentence A is the first text data.

[0057] The data DA2 obtained through such processing is transmitted from the information processing device 10 to the information processing device 40 via the network 30a.

[0058] Next, data DB1 is transmitted from information processing device 40 to information processing device 10 via network 30b. That is, information processing device 10 acquires data DB1 from information processing device 40 via network 30b. Data DB1 is text data equivalent to a response sentence corresponding to data DA2 input to information processing device 40. Details of data DB1 will be explained later in <Information Processing Method 1>.

[0059] Next, the information processing device 10 creates a data DB2 based on the data DB1. The data DB2 is the data DA1 updated based on the data DB1. The data DB2 is result data to be output from the information processing device 10 to the information terminal 20. Details of the data DB2 will be explained later in <Information processing method 1>.

[0060] Next, the information processing device 10 outputs the data DB2 via the network 31b to the information terminal 20. As a result, the user can obtain the data DB2 created by updating the data DA1.

[0061] For example, data DB2 may be converted into data other than text data and then output to information terminal 20. For example, if data DA1 is data other than text data, data DB2 is preferably data in the same format as data DA1. Information processing device 10 may have a function of generating image data using text data, for example.

[0062] Fig. 3 is a block diagram of the information processing system shown in Fig. 1. In Fig. 3, an example of the configuration of the information processing device 10 will be mainly described.

[0063] The information processing device 10 includes a receiving unit 110 , a storage unit 120 , a processing unit 130 , an output unit 140 , and a transmission path 150 .

[0064] In the drawings accompanying this specification, the components are classified by function and shown as independent blocks in the block diagrams. However, in reality, it is difficult to completely separate the components by function, and one component may be involved in multiple functions. For example, part of the processing unit 130 may function as the reception unit 110. Also, one function may be involved in multiple components. For example, the processing performed by the processing unit 130 may be executed by different servers depending on the processing.

[0065] [Reception unit 110] The reception unit 110 can receive data from outside the information processing device 10. For example, the reception unit 110 receives data from the information terminal 20 via the network 31a. The data received from the information terminal 20 corresponds to the data DA1 described above. Furthermore, for example, the reception unit 110 receives data from the information processing device 40 via the network 30b. The data received from the information processing device 40 corresponds to the data DB1 described above.

[0066] As described above, it is preferable that the data accepted by the accepting unit 110 is text data. Furthermore, if the data accepted by the accepting unit 110 is data other than text data, it is preferable that the processing unit 130 generates text data using the data accepted by the accepting unit 110.

[0067] The data supplied to the reception unit 110 is supplied to one or both of the storage unit 120 and the processing unit 130 via the transmission path 150. Furthermore, the reception unit 110 may be, for example, a communication port or an input device such as a personal computer equipped with a communication function.

[0068] [Storage Unit 120] The storage unit 120 has a function of storing a program executed by the processing unit 130. The storage unit 120 may also have a function of storing data created by the processing unit 130 (e.g., calculation results, analysis results, inference results), data input to the reception unit 110, etc.

[0069] The storage unit 120 preferably has a function of storing instruction sentences in the prompts. Details of the instruction sentences in the prompts will be explained later in <Information processing method 1>.

[0070] The storage unit 120 may have a database. Furthermore, the information processing device 10 may have a database separate from the storage unit 120. The information processing device 10 may have a function to retrieve data from a database that exists outside the storage unit 120, outside the information processing device 10, or outside the information processing system. Furthermore, the information processing device 10 may have a function to retrieve data from both its own database and an external database.

[0071] A file server may be used instead of the database. For example, when using files stored in a file server, it is preferable that the database has paths to files stored in the file server.

[0072] The storage unit 120 includes at least one of a volatile memory and a non-volatile memory. Examples of the volatile memory include a dynamic random access memory (DRAM) and a static random access memory (SRAM). Examples of the non-volatile memory include a resistive random access memory (ReRAM), a phase change random access memory (PRAM), a ferroelectric random access memory (FeRAM), a magnetoresistive random access memory (MRAM), and a flash memory. The storage unit 120 may also include at least one of NOSRAM (registered trademark) and DOSRAM (registered trademark). The storage unit 120 may also include a recording media drive. Examples of recording media drives include a hard disk drive (HDD) and a solid state drive (SSD).

[0073] NOSRAM is an abbreviation for "Nonvolatile Oxide Semiconductor Random Access Memory (RAM)." NOSRAM is a memory in which memory cells are two-transistor (2T) or three-transistor (3T) gain cells, and the transistors are transistors (also called OS transistors) that use metal oxide in their channel formation regions. OS transistors have an extremely small leakage current, i.e., a current that flows between the source and drain in an off state. NOSRAM can be used as a nonvolatile memory by retaining a charge corresponding to data in the memory cell using its extremely small leakage current characteristic. In particular, NOSRAM can read stored data without destroying it (nondestructive read), making it suitable for arithmetic processing in which only data read operations are repeated in large quantities. NOSRAM can increase its data capacity by stacking layers, and therefore can be used as a large-scale cache memory, main memory, or storage memory to improve the performance of semiconductor devices.

[0074] DOSRAM is an abbreviation for "Dynamic Oxide Semiconductor RAM" and refers to a RAM having 1T (transistor) 1C (capacitor) type memory cells. DOSRAM is a DRAM formed using OS transistors, and is a memory that temporarily stores information sent from an external device. DOSRAM is a memory that takes advantage of the low off-state current of OS transistors.

[0075] In this specification and the like, a metal oxide refers to an oxide of a metal in a broad sense. Metal oxides are classified into oxide insulators, oxide conductors (including transparent oxide conductors), oxide semiconductors (also referred to as oxide semiconductors or simply as OSs), and the like. For example, when a metal oxide is used for a semiconductor layer of a transistor, the metal oxide may be referred to as an oxide semiconductor.

[0076] The metal oxide included in the channel formation region preferably contains indium (In). When the metal oxide included in the channel formation region contains indium, the carrier mobility (electron mobility) of the OS transistor is increased. Furthermore, the metal oxide included in the channel formation region is preferably an oxide semiconductor containing element M. The element M is preferably at least one of aluminum (Al), gallium (Ga), and tin (Sn). Other elements applicable to element M include boron (B), silicon (Si), titanium (Ti), iron (Fe), nickel (Ni), germanium (Ge), yttrium (Y), zirconium (Zr), molybdenum (Mo), lanthanum (La), cerium (Ce), neodymium (Nd), hafnium (Hf), tantalum (Ta), and tungsten (W). However, a combination of two or more of the above elements may be used as element M. The element M is, for example, an element having a high bond energy with oxygen. For example, it is an element having a higher bond energy with oxygen than indium. The metal oxide contained in the channel formation region is preferably a metal oxide containing zinc (Zn), since zinc-containing metal oxides may be easily crystallized.

[0077] The metal oxide contained in the channel formation region is not limited to a metal oxide containing indium, but may be, for example, a metal oxide containing zinc but not indium, such as zinc tin oxide or gallium tin oxide, a metal oxide containing gallium, or a metal oxide containing tin.

[0078] [Processing Unit 130] The processing unit 130 has a function of performing processes such as calculation, analysis, and inference using data supplied from one or both of the receiving unit 110 and the storage unit 120. The processing unit 130 can supply the created data (e.g., calculation results, analysis results, and inference results) to one or both of the storage unit 120 and the output unit 140.

[0079] The processing unit 130 has a function of acquiring data from the storage unit 120. The processing unit 130 may also have a function of recording or registering data in the storage unit 120.

[0080] The processing unit 130 has a function of extracting components from a document included in the document data. For example, the processing unit 130 has a function of extracting at least one first component from a first document included in the document data. Here, the text form of the first component extracted by the processing unit 130 is not limited. For example, the first component extracted by the processing unit 130 may be a word, a phrase, a clause, a sentence, or a paragraph. Note that the document data is data received by the receiving unit 110 and corresponds to data DA1.

[0081] The processing unit 130 has a function of creating a first prompt including a first component, a second document, and a first instruction. The first instruction includes an instruction to extract at least one description corresponding to the first component from the second document. Therefore, the first prompt can be called a description extraction prompt. The created first prompt corresponds to data DA2.

[0082] Moreover, the above description can be considered as a description of a specific example corresponding to the first component.

[0083] The processing unit 130 has a function of causing the language model to generate a response sentence from the prompt via the transmission path 150, the output unit 140, and the network 30a. For example, the processing unit 130 has a function of causing the language model to generate a first response sentence from a first prompt via the transmission path 150, the output unit 140, and the network 30a. The first response sentence includes the above-mentioned description. The first response sentence corresponds to data DB1.

[0084] The processing unit 130 has a function of determining whether the above-mentioned descriptions conform to the regulations. For example, the processing unit 130 has a function of performing a first determination on the descriptions and creating a first determination result. The first determination determines, for each of the descriptions, whether the number of the above-mentioned specific examples included in the description conforms to the regulations, for example, whether the number reaches the specified number. Furthermore, if the first determination result is non-conforming, the processing unit 130 has a function of including the value of the number of the above-mentioned specific examples that is missing in the first determination result.

[0085] The processing unit 130 has a function of generating a second prompt including the first determination result, the first component, the above-mentioned description, and a second instruction. The second instruction includes an instruction to present a first proposed revision to bring the description into conformity with the above-mentioned specification if it is determined based on the first determination result that the description does not conform to the specification. From the above, the second prompt can be called a revision generation prompt. The generated second prompt corresponds to data DA2. The first proposed revision includes the description and includes revision examples generated to match the number of specific examples described above that are missing due to the first determination.

[0086] The processing unit 130 has a function of causing the language model to generate a second response sentence from the second prompt via the transmission path 150, the output unit 140, and the network 30a. The second response sentence includes the first proposed revision. The second response sentence corresponds to the data DB1.

[0087] The processing unit 130 has a function of generating first result data based on the first component, the above description, and the first proposed revision. The processing unit 130 has a function of outputting the first result data to the information terminal 20. The first result data may include the first determination result, the first component, the description, and the first proposed revision. The first result data may be displayed on a graphical user interface (GUI). The type of GUI that displays the first result data is not limited. For example, it is preferable to display the first result data on a tabular GUI. The generated first result data corresponds to the data DB2.

[0088] The processing unit 130 has a function of creating a third prompt including a first component, a first proposed revision, and a third instruction. The third instruction includes an instruction to present at least one proposed description corresponding to the first proposed revision. Furthermore, the proposed description may be, for example, a description that has been abstracted from the first proposed revision. Thus, the third prompt may be called an abstraction prompt. The created third prompt corresponds to data DA2.

[0089] The processing unit 130 has a function of causing the language model to generate a third response sentence from the third prompt via the transmission path 150, the output unit 140, and the network 30a. The third response sentence includes the above-mentioned writing plan. The third response sentence corresponds to the data DB1.

[0090] The processing unit 130 has a function of generating second result data based on the first component, the first proposed revision, and the above-mentioned proposed description. The processing unit 130 has a function of outputting the second result data to the information terminal 20. The second result data may include the first component, the first proposed revision, and the proposed description. The second result data may be displayed on a GUI. The type of GUI that displays the second result data is not limited. For example, it is preferable to display the second result data on a tabular GUI. The generated second result data corresponds to the data DB2.

[0091] The processing unit 130 has a function of extracting components and descriptions related to the components from a document included in the document data. Specifically, the processing unit 130 has a function of extracting at least one second component and at least one first numerical constraint corresponding to the second component from a first document. Specifically, the processing unit 130 has a function of determining whether the first document has a first numerical constraint for each second component, and extracting the second component determined to have a numerical constraint and the first numerical constraint corresponding to the second component. Here, the text form of the second component extracted by the processing unit 130 is not limited. For example, the second component extracted by the processing unit 130 may be a word, phrase, clause, sentence, or paragraph. Note that the document data is data received by the receiving unit 110 and corresponds to data DA1.

[0092] The processing unit 130 also has a function of generating a fourth prompt including a second document, a second component, and a fourth instruction. The fourth instruction includes an instruction to extract at least one second numerical constraint corresponding to the second component from the second document. Therefore, the fourth prompt can be called a numerical constraint extraction prompt. The generated fourth prompt corresponds to data DA2.

[0093] For example, the processing unit 130 has a function of causing the language model to generate a fourth response sentence from the fourth prompt via the transmission path 150, the output unit 140, and the network 30a. The fourth response sentence includes the second numerical restriction. The acquired fourth response sentence corresponds to the data DB1.

[0094] The processing unit 130 has a function of determining whether the second numerical limitation conforms to the regulations. For example, the processing unit 130 performs a second determination on the second numerical limitation and generates a second determination result. In the second determination, the processing unit 130 determines whether the range of the second numerical limitation matches the range of the first numerical limitation.

[0095] The processing unit 130 has a function of generating a fifth prompt including the second determination result, the second component, the first numerical constraint, the second numerical constraint, and a fifth instruction. The fifth instruction includes an instruction to present at least one second revision proposal for making the second numerical constraint conform to the above-mentioned specification if it is determined that the second numerical constraint does not conform to the specification. From the above, the fifth prompt can be called a revision proposal generation prompt. The generated fifth prompt corresponds to data DA2.

[0096] The processing unit 130 has a function of causing the language model to generate a fifth response sentence from the fifth prompt via the transmission path 150, the output unit 140, and the network 30a. The fifth response sentence includes at least one second revision suggestion. The acquired fifth response sentence corresponds to data DB1.

[0097] The processing unit 130 has a function of generating third result data based on the second component, the first numerical limitation, the second numerical limitation, and the second proposed revision. The processing unit 130 has a function of outputting the third result data to the information terminal 20. The third result data may include the second judgment result, the second component, the first numerical limitation, the second numerical limitation, and the second proposed revision. The third result data may be displayed on a GUI. The type of GUI that displays the third result data is not limited. For example, it is preferable to display the third result data on a tabular GUI. The generated third result data corresponds to the data DB2.

[0098] The processing unit 130 may include, for example, an arithmetic circuit, a central processing unit (CPU), and a graphics processing unit (GPU).

[0099] The processing unit 130 may have a microprocessor such as a DSP (Digital Signal Processor). The microprocessor may be implemented by a PLD (Programmable Logic Device) such as an FPGA (Field Programmable Gate Array) or an FPAA (Field Programmable Analog Array). The processing unit 130 may also have a quantum processor. The processing unit 130 can perform various data processing and program control by interpreting and executing instructions from various programs using the processor. Programs that can be executed by the processor are stored in at least one of the memory area of ​​the processor and the storage unit 120.

[0100] The processing unit 130 may include a main memory. The main memory may include at least one of a volatile memory such as a random access memory (RAM) and a non-volatile memory such as a read-only memory (ROM). The main memory may also include at least one of the above-mentioned NOSRAM and DOSRAM.

[0101] The RAM may be, for example, a DRAM or an SRAM, and a virtual memory space is allocated and used as a working space for the processing unit 130. The operating system, application programs, program modules, program data, lookup tables, and the like stored in the storage unit 120 are loaded into the RAM for execution. The data, programs, and program modules loaded into the RAM are each directly accessed and operated by the processing unit 130.

[0102] The ROM can store a BIOS (Basic Input / Output System), firmware, etc., which do not require rewriting. Examples of ROM include mask ROM, OTPROM (One Time Programmable Read Only Memory), and EPROM (Erasable Programmable Read Only Memory). Examples of EPROMs include UV-EPROMs (Ultra-Violet Erasable Programmable Read Only Memories), which allow stored data to be erased by exposure to ultraviolet light, EEPROMs (Electrically Erasable Programmable Read Only Memories), and flash memories.

[0103] The processing section 130 can include one or both of an OS transistor and a transistor having silicon in a channel formation region (a Si transistor).

[0104] The processing unit 130 preferably includes an OS transistor. Because an OS transistor has an extremely small off-state current, using the OS transistor as a switch for retaining charge (data) flowing into a capacitor functioning as a memory element can ensure a long data retention period. By using this characteristic in at least one of the register and cache memory of the processing unit, the processing unit can be operated only when necessary, and can be turned off in other cases by saving information from the previous processing in the memory element. In other words, normally-off computing is possible, and the power consumption of the information processing system can be reduced.

[0105] [Output Unit 140] The output unit 140 has a function of outputting data based on the processing result of the processing unit 130. The output unit 140 can supply at least one of the calculation result, analysis result, and inference result of the processing unit 130 to an external device of the information processing device 10.

[0106] The output unit 140 can output data to the outside of the information processing device 10. For example, the output unit 140 outputs data to the information terminal 20 via the network 31b. The output unit 140 can output data created by the processing unit 130 based on data received from the information processing device 40 to the information terminal 20. Alternatively, the output unit 140 can output the data itself received from the information processing device 40 to the information terminal 20. The data output to the information terminal 20 corresponds to the data DB 2 described above.

[0107] The data can be presented, for example, by displaying it on the display screen of the information terminal 20, or by outputting a file in txt format, docx format, xml format, pdf format, csv format, or other format.

[0108] Furthermore, the output unit 140 outputs data to the information processing device 40 via the network 30a. The output unit 140 outputs data created by the processing unit 130 based on data received from the information terminal 20 to the information processing device 40. The data output to the information processing device 40 corresponds to the data DA2 described above. Furthermore, the output unit 140 may be, for example, a communication port or a device such as a personal computer equipped with a communication function.

[0109] [Transmission Path 150] The transmission path 150 has a function of transmitting data. Data can be transmitted and received between the reception unit 110, the storage unit 120, the processing unit 130, and the output unit 140 via the transmission path 150. Specifically, a LAN or the Internet can be used.

[0110] <Information Processing Method 1> The information processing system of this embodiment can perform the processes of steps S01 to S08 shown in FIG. 4. FIGS. 6A to 6D and 8A to 10B are diagrams illustrating an information processing method that can be performed by the information processing system of this embodiment. FIGS. 8A, 9, and 10B can also be considered examples of GUIs related to the information processing system of this embodiment. Forms, icons, tables, etc. in the drawings related to the GUI illustrated in this embodiment, such as FIG. 8A, are examples. The GUI can be configured as a web page accessed by a user via a network. Alternatively, the GUI can be configured as a screen of a program application executed on a terminal used by the user. FIGS. 8A to 9 and 10B show an example of instructing a language model to extract descriptions contained in a document, determine the descriptions, and present a revision proposal based on the determination results.

[0111] [Step S01] In step S01, the receiving unit 110 receives document data including document 301 and document 303. Specifically, the receiving unit 110 receives the document data via the information terminal 20. The document data corresponds to the above-mentioned data DA1. For example, document 301 may be a patent claim, and document 303 may be a specification related to document 301. Document 301 corresponds to the above-mentioned first document, and document 303 corresponds to the above-mentioned second document. In the information processing method of this embodiment, a case will be described in which the receiving unit 110 receives document data including document 301 and document 303.

[0112] For example, the user inputs document data including document 301 and document 303 into the information processing device 10 using the information terminal 20. Alternatively, for example, the user may specify document data stored in the storage unit 120.

[0113] [Step S02] In step S02, the processing unit 130 extracts at least one component 302 from the document 301. Here, the text form of the extracted component 302 is not limited. Examples of the component 302 include a word, a phrase, a clause, a sentence, and a paragraph. The component 302 corresponds to the first component described above.

[0114] For example, as shown in FIG. 6A, a component 302 included in a document 301 is extracted by the processing unit 130 .

[0115] In the information processing method of this embodiment, a case will be described in which n (n is an integer greater than or equal to 1) components 302 (such as component 302[1] shown in FIG. 6A as an example) are extracted from a document 301.

[0116] The extraction process of the constituent elements 302 may be performed by a language model.

[0117] [Step S03] In step S03, the processing unit 130 creates a prompt 401. The prompt 401 corresponds to the first prompt described above.

[0118] The prompt 401 includes a component 302, a document 303, and a first instruction statement. The first instruction statement includes an instruction to extract at least one description 305 corresponding to the component 302 from the document 303.

[0119] Furthermore, the description 305 may be a description of a specific example corresponding to the component 302, for example. Note that the description 305 to be extracted is not limited to a description of a specific example. For example, it may be a description of the principle, action, and effect related to the configuration. Furthermore, the description 305 may include descriptions of multiple specific examples, or may not include any description of a specific example. In the latter case, in the information processing method of this embodiment, the value of the specific example included in the description 305 is treated as "NULL."

[0120] The first directive includes an instruction to perform the extraction process. For example, directives such as "Extract from the document a description that includes at least one specific example corresponding to each component. If no specific examples are included, return 'NULL'"; "Extract from the document a description that includes at least one principle corresponding to each component. If no principles are included, return 'NULL'"; "Extract from the document a description that includes at least one action corresponding to each component. If no actions are included, return 'NULL'"; or "Extract from the document a description that includes at least one effect corresponding to each component. If no effects are included, return 'NULL'" may be presented. The processing unit 130 can generate the prompt 401 using the document 303, the component 302, and the first directive.

[0121] Prompt 401 does not necessarily include the entire document 303, but may include only a portion of document 303. For example, if document 303 is a specification belonging to a patent application, prompt 401 may include embodiments and examples extracted from document 303.

[0122] [Step S04] In step S04, the processing unit 130 causes the language model to generate a response sentence 501 from the prompt via the network 30. The response sentence 501 includes a description 305. For example, as shown in FIG. 6B , the processing unit 130 transmits the prompt 401 to the language model 210, thereby generating a response sentence 501 in response to the prompt 401. The response sentence 501 corresponds to the first response sentence described above.

[0123] In the information processing method of this embodiment, a case where the description 305 included in the response sentence 501 includes at least one specific example corresponding to the component 302 and a case where the description 305 does not include any specific examples will be described. The response sentence 501 includes, for example, a description 305[1] corresponding to the component 302[1]. Specifically, the description 305[1] includes a description of a specific example of the component 302[1]. Furthermore, for example, the description 305[1] includes at least one specific example 306 or "NULL". The specific example 306 is one of the descriptions of specific examples extracted from the document 303. When there are multiple components 302, the number of specific examples 306 included in the description 305 may differ for each component 302. Here, the form of the text of the extracted description 305 is not limited. Examples of the description 305 include a word, a phrase, a clause, a sentence, or a paragraph.

[0124] [Step S05] In step S05, the processing unit 130 determines whether the description 305 conforms to the regulations. For example, as shown in FIG. 6C , a determination 201 is performed on the description 305, and a determination result 203 is generated. Here, the condition that the description 305 conforms to the regulations refers to a state in which the number of specific examples 306 included in the description 305 reaches a specified number. If the result of the determination 201 shows that the description 305 does not conform to the regulations, the value of the number of missing specific examples 306 can be included in the determination result 203. The determination 201 corresponds to the first determination described above. The determination result 203 corresponds to the first determination result described above.

[0125] The above-mentioned specified number can be set as an initial value, for example. Alternatively, the specified number can be specified by inputting an arbitrary value into a GUI such as an edit box (text box). In the information processing method of this embodiment, a case where the specified number is specified by the latter method will be described.

[0126] 8A shows an example in which the extracted description 305 is displayed on the display unit of the information terminal 20 immediately after step S04. In the example shown in FIG. 8A, the components 302 and the description 305 are displayed in a tabular GUI. Also shown is an example in which a GUI of an edit box 321 for specifying the specified number as "X" and a button 323 for executing processing is displayed above the table.

[0127] As described above, in step S04, at least one description 305 corresponding to a component 302 is extracted, and the extracted description 305 includes at least one specific example 306 or "NULL." Therefore, the table shown in FIG. 8A shows an example in which the column for component 302 includes components 302[1] through 302[n], and the column for description 305 includes descriptions 305[1] through 305[n]. Furthermore, the table shows an example in which descriptions 305[1] through 305[n] each include specific examples 306[1] through 306[n]. Specifically, description 305[1] corresponding to component 302[1] includes three specific examples, 306[1,1] to 306[1,3]; description 305[2] corresponding to component 302[2] includes five specific examples, 306[2,1] to 306[2,5]; description 305[3] corresponding to component 302[3] includes two specific examples, 306[3,1] and 306[3,2]; description 305[4] corresponding to component 302[4] does not include specific example 306; and description 305[n] corresponding to component 302[n] includes one specific example, 306[n,1].

[0128] The user can use a keyboard or the like to input an arbitrary number "X" into edit box 321 displayed on the display unit of information terminal 20, thereby specifying the specified number as "X." For example, the processing result when determination 201 is executed by the user inputting "5" into edit box 321 in Fig. 8A and clicking button 323 using mouse pointer 325 is shown in Fig. 8B.

[0129] 8B shows an example in which the processing unit 130 generates a judgment result 203 based on the result of the aforementioned judgment 201. For example, if the number of specific examples 306 is equal to or greater than a specified number, the judgment result 203 is "TRUE," and if the number is less than the specified number, the judgment result 203 is "FALSE." Furthermore, if the judgment result 203 is "FALSE," the processing unit 130 can also include in the judgment result 203 a value obtained by subtracting the number of specific examples 306 from the specified number. Specifically, since the number of specific examples 306[1] included in the description 305[1] corresponding to the component 302[1] is three, the value of the judgment result 203 is "FALSE." Furthermore, the processing unit 130 can include in the judgment result 203 a value "2" obtained by subtracting "3" from the specified number "5." For example, the generated judgment result 203 can be expressed as "FALSE<2>." Note that the processing unit 130 can make the judgment 201 even if the description 305 corresponding to the component 302 does not include any specific examples 306. Specifically, since the value of the description 305[4] corresponding to the component 302[4] is "NULL", the processing unit 130 can include the value "5" obtained by subtracting "0" from the specified number "5" in the judgment result 203. For example, the created judgment result 203 can be expressed as "FALSE<5>".

[0130] [Step S06] In step S06, the processing unit 130 creates a prompt 403. The prompt 403 corresponds to the second prompt described above.

[0131] The prompt 403 is a prompt for obtaining at least one proposed revision 307 corresponding to the description 305 based on the determination result 203. The prompt 403 includes the determination result 203, the component 302, the description 305, and a second instruction. The second instruction includes an instruction to present at least one proposed revision 307 for making the description 305 conform to the specification, if it is determined based on the determination result 203 that the description 305 does not conform to the specification. The second instruction can be, for example, "If the determination result is 'FALSE,' please generate a proposed revision including additional revision examples for the number of specific examples included in the description corresponding to the component that is less than the specified number." The proposed revision 307 corresponds to the first proposed revision described above.

[0132] [Step S07] In step S07, the processing unit 130 causes the language model to generate a response sentence 503 from the prompt via the network 30. The response sentence 503 includes at least one revision suggestion 307. For example, as shown in FIG. 6D , the processing unit 130 transmits the prompt 403 to the language model 220, thereby generating a response sentence 503 in response to the prompt 403. The response sentence 503 corresponds to the second response sentence described above.

[0133] The proposed revision 307 includes the description 305, and includes revision examples 308 generated in the same number as the number of specific examples determined to be insufficient by the determination 201. The revision examples 308 may be descriptions of specific examples generated by a language model, for example. In the information processing method of this embodiment, a case will be described in which the revision examples 308 included in the proposed revision 307 are descriptions of specific examples corresponding to the components 302. Note that the revision examples 308 are not limited to descriptions of specific examples. For example, they may be descriptions of principles, actions, and effects related to the configuration.

[0134] For example, if the determination result 203 included in the prompt 403 is "FALSE", revision examples 308 are generated by the language model for the number of missing specific examples. Also, if the determination result 203 included in the prompt 403 is "TRUE", revision examples 308 are not generated. In the latter case, the revision proposal 307 includes only the description 305, and does not include the revision examples 308. In the information processing method of this embodiment, a case will be described in which the language model generates n revision proposals 307 for n descriptions 305 corresponding to n components 302.

[0135] [Step S08] In step S08, the processing unit 130 generates result data 315 based on the components 302, descriptions 305, and proposed revisions 307. FIG. 9 illustrates an example in which the generated result data 315 is output to the display unit of the information terminal 20. In the example illustrated in FIG. 9, the components 302, descriptions 305, and proposed revisions 307, in addition to the judgment result 203, are displayed in a tabular GUI. Furthermore, descriptions 305[1] through 305[n] within the table display specific examples 306[1] through 306[n], respectively. Furthermore, proposed revisions 307[1] through 307[n] display specific examples 306[1] through 306[n], respectively, and revision examples 308[1] through 308[n], respectively. Furthermore, an example is illustrated in which GUIs of an edit box 321, a button 323, and a button 327 are displayed above the table. Furthermore, the specified number "X" input by the user in the above-mentioned step S05 can be displayed in the edit box 321. For example, the specified number "X" may be set to "5" input by the user in the above-mentioned step S05. The result data 315 corresponds to the above-mentioned first result data.

[0136] 9 shows an example including descriptions 305[1] through 305[n] and proposed revisions 307[1] through 307[n] corresponding to components 302[1] through 302[n]. Descriptions 305[1] through 305[n] include specific examples 306[1] through 306[n], respectively, and proposed revisions 307[1] through 307[n] include descriptions 305[1] through 305[n], and, if the determination result 203 is "FALSE," revised examples 308[1] through 308[n], respectively. Specifically, description 305[1] corresponding to component 302[1] includes three specific examples (specific examples 306[1,1] to 306[1,3]), and revision proposal 307[1] includes description 305[1] as well as two additional examples (additional examples 308[1,1] and 308[1,2]). Description 305[2] corresponding to component 302[2] includes five specific examples (specific examples 306[2,1] to 306[2,5]), and revision proposal 307[2] includes only description 305[2]. Furthermore, description 305[3] corresponding to component 302[3] includes two specific examples (specific example 306[3,1] and specific example 306[3,2]), and revision proposal 307[3] includes three revision examples (revision examples 308[3,1] to 308[3,3]) in addition to description 305[3]. Furthermore, description 305[4] corresponding to component 302[4] does not include specific example 306, and revision proposal 307[4] includes five revision examples (revision examples 308[4,1] to 308[4,5]). Furthermore, description 305[n] corresponding to component 302[n] includes one specific example 306[n,1], and revision proposal 307[n] includes four revision examples (revision examples 308[n,1] to 308[n,4]) in addition to description 305[n]. Here, to make it easier to understand that revision example 308 has been added, it is preferable to also display the determination result 203. It is also preferable to highlight revision example 308. For example, the revision example 308 can be highlighted by changing the text color, increasing the text size, changing the font, making it bold, underlining, or adding a background color.

[0137] It is also possible to change the number of generated revision examples 308. For example, the user can repeatedly perform the processes of steps S05 to S08 by inputting a numerical value into an edit box 321 using a keyboard or the like and clicking a button 323 using a mouse pointer 325, as shown in FIG.

[0138] Furthermore, the processing unit 130 can create a prompt 404 based on the generated revision proposal 307. The prompt 404 includes the component 302, the revision proposal 307, and a third instruction. The third instruction includes a command to present at least one writing proposal 309 corresponding to the revision proposal 307. The writing proposal 309 can be, for example, a description obtained by abstracting a specific example included in the revision proposal 307 (hereinafter, an abstract example). In the information processing method of this embodiment, a case will be described in which the writing proposal 309 includes at least one abstract example corresponding to the revision proposal 307. The prompt 404 corresponds to the third prompt described above.

[0139] The third instruction sentence may be, for example, "Please generate a description proposal including an abstract example corresponding to the revision proposal." For example, as shown in FIG. 10A , a prompt 404 is sent to the language model 225 to generate a response sentence 504 in response to the prompt 404. The response sentence 504 includes the description proposal 309. Furthermore, the prompt 404 can be created and sent to the language model by the user clicking a button 327 using a mouse pointer 325, as shown in FIG. 9 . The response sentence 504 corresponds to the third response sentence described above.

[0140] 10B shows an example in which result data is generated based on the component 302, the proposed revision 307, and the proposed description 309 and output to the display unit of the information terminal 20. In the example shown in FIG. 10B, the component 302, the proposed revision 307, and the proposed description 309 are displayed in a tabular GUI. Specifically, the example shows proposed revision 307[1] and proposed description 309[1] corresponding to the component 302[1], proposed revision 307[2] and proposed description 309[2] corresponding to the component 302[2], proposed revision 307[3] and proposed description 309[3] corresponding to the component 302[3], proposed revision 307[4] and proposed description 309[4] corresponding to the component 302[4], and proposed revision 307[n] and proposed description 309[n] corresponding to the component 302[n]. The number of abstract examples to be generated in each of the proposed descriptions 309[1] to 309[n] can be set as an initial value, for example. The predetermined number can also be specified by inputting an arbitrary value into a GUI such as an edit box. Specifically, as shown in FIG. 9 , the user can specify the number of abstract examples to be generated by inputting an arbitrary value into the edit box 321 and clicking the button 327 using the mouse pointer 325. The specified predetermined number can be included in the prompt 404. The execution of the process using the buttons 323 and 327 is not limited to clicking with a mouse. For example, the process may be performed by pressing a predetermined key or the like while the button is focused. This result data corresponds to the second result data described above.

[0141] As described above, the language model can be used to confirm suggested corrections to descriptions in a document. Furthermore, the document proofreading process using the language model can be supported. Note that the language model 210, the language model 220, and the language model 225 may be the same model or different models. For example, if the same model is used, the system can be simplified. Furthermore, if different models are used, the system can be made lighter and optimized. Specifically, by using BERT for the language model 210 that extracts descriptions from a document, the generation of a prompt in the processing unit 130 can be omitted.

[0142] <Information Processing Method 2> The information processing system of this embodiment can perform the processes of steps S11 to S18 shown in Fig. 5. Figs. 7A to 7D, 11A, and 11B are diagrams explaining an information processing method that can be performed by the information processing system of this embodiment. Fig. 11B can also be said to be an example of a GUI related to the information processing system of this embodiment. Figs. 11A and 11B show an example of a case in which a language model is instructed to extract descriptions contained in a document and present a revision proposal based on the determination results.

[0143] [Step S11] In step S11, the receiving unit 110 receives document data including document 301 and document 303. Specifically, the receiving unit 110 receives the document data via the information terminal 20. The document data corresponds to the above-mentioned data DA1. For example, document 301 may be a patent claim, and document 303 may be a specification related to document 301. Document 301 corresponds to the above-mentioned first document, and document 303 corresponds to the above-mentioned second document. In the information processing method of this embodiment, a case will be described in which the receiving unit 110 receives document data including document 301 and document 303.

[0144] For example, similar to the above-described <Information Processing Method 1>, the user inputs document data including documents 301 and 303 into the information processing device 10 using the information terminal 20. Alternatively, for example, the user may specify document data stored in the storage unit 120.

[0145] [Step S12] In step S12, the processing unit 130 extracts at least one component 304 and at least one numerical constraint 310 corresponding to the component 304 from the document 301. Specifically, the processing unit 130 determines whether the document 301 has a numerical constraint for each component 304, and extracts the component 304 determined to have a numerical constraint and the numerical constraint 310 corresponding to the component 304. The form of the component 304 is not limited. Examples of the extracted component 304 include a word, phrase, clause, sentence, or paragraph. The component 304 corresponds to the second component described above. The numerical constraint 310 corresponds to the first numerical constraint described above.

[0146] For example, as shown in FIG. 7A, a component 304 included in a document 301 and a numerical constraint 310 corresponding to the component 304 are extracted by the processing unit 130.

[0147] In the information processing method of this embodiment, a case will be described in which n numerical constraints 310 (numerical constraints 310[1] to 310[n]) are extracted from n (n is an integer greater than or equal to 1) components 304 (component 304[1] to component 304[n]) extracted from a document 301. Each of the numerical constraints 310[1] to 310[n] may contain multiple numerical constraint descriptions. Furthermore, the numerical constraints 310[1] to 310[n] may contain similar numerical constraint descriptions. Specifically, for example, the numerical constraint description included in the numerical constraint 310[1] and the numerical constraint description included in the numerical constraint 310[2] may be the same in part or in whole.

[0148] If the number of numerical constraints extracted from document 301 in step S12 is zero, the process can be terminated without proceeding to the subsequent steps. At this time, it is preferable to output text such as "No numerical constraints found" and display it on the display unit of information terminal 20.

[0149] [Step S13] In step S13, the processing unit 130 creates a prompt 405. The prompt 405 corresponds to the fourth prompt described above.

[0150] Prompt 405 includes document 303, component 304, and a fourth directive. The fourth directive includes an instruction for document 303 to extract at least one numerical constraint 311 corresponding to component 304. Numeric constraint 311 corresponds to the second numerical constraint described above.

[0151] In the information processing method of this embodiment, a case will be described in which n numerical constraints 311 (numerical constraints 311[1] to 311[n]) are extracted from a document 303 for n components 304[1] to 304[n]. Furthermore, each of the numerical constraints 311[1] to 311[n] may contain multiple numerical constraint descriptions, or none at all. For example, even if no numerical constraint description corresponding to a component 304 exists, it can be extracted as a numerical constraint 311 containing a value of "NULL." Furthermore, the same numerical constraint 311 can be extracted multiple times for different components 304.

[0152] The fourth directive includes an instruction to perform the extraction process described above. For example, a directive such as "Extract from the document a description that includes at least one numerical constraint corresponding to each component. If no numerical constraint is included, return 'NULL'" is presented. The processing unit 130 can create a prompt 405 using the document 303, the component 304, and the fourth directive.

[0153] Prompt 405 may not include the entire document 303, but may include only a portion of document 303. For example, if document 303 is a specification belonging to a patent application, examples extracted from document 303 may be included in prompt 405.

[0154] [Step S14] In step S14, the processing unit 130 causes the language model to generate a response sentence 505 from the prompt via the network 30. The response sentence 505 includes a numerical constraint 311. For example, as shown in FIG. 7B , the processing unit 130 transmits the prompt 405 to the language model 230, thereby generating a response sentence 505 in response to the prompt 405. The response sentence 505 corresponds to the fourth response sentence described above.

[0155] The response sentence 505 includes, for example, numerical constraints 311[1] through 311[n] corresponding to the components 304[1] through 304[n].

[0156] [Step S15] In step S15, the processing unit 130 determines whether the numerical restriction 311 conforms to the regulations. For example, as shown in FIG. 7C , the processing unit 130 performs determination 205 on the numerical restriction 311 and generates determination result 207. In determination 205, for example, it is determined whether the range of the numerical restriction 311 matches the range of the numerical restriction 310. Determination 205 corresponds to the second determination described above. Determination result 207 corresponds to the second determination result described above.

[0157] As a result of the determination 205, for example, if the ranges of the numerical constraints 310 and 311 corresponding to the component 304 match, a determination result 207 of "TRUE" is obtained, and if they do not match or are "NULL", a determination result of "FALSE" is obtained.

[0158] The information processing method of this embodiment will be described based on an example of the determination results shown in Fig. 11A. For example, Fig. 11A shows an example in which the determination results 207 of the numerical constraints 310[1] and 311[1] corresponding to the component 304[1], the numerical constraints 310[2] and 311[2] corresponding to the component 304[2], the numerical constraints 310[3] and 311[3] corresponding to the component 304[3], and the numerical constraints 310[n] and 311[n] corresponding to the component 304[n] are "TRUE", "FALSE", "TRUE", and "FALSE", respectively.

[0159] If all the determination results 207 are "TRUE", the process can be terminated without proceeding to the subsequent steps. At this time, it is preferable to output a text message such as "No parts requiring correction were found" and display it on the display unit of the information terminal 20.

[0160] [Step S16] In step S16, the processing unit 130 creates a prompt 407. The prompt 407 corresponds to the fifth prompt described above.

[0161] The prompt 407 is a prompt for obtaining at least one proposed revision 313 corresponding to the numerical constraint 311 based on the judgment result 207. The prompt 407 includes the judgment result 207, the component 304, the numerical constraint 310, the numerical constraint 311, and a fifth instruction. At this time, the component 304, the numerical constraint 310, and the numerical constraint 311 for which the judgment result 207 is "TRUE" are not included in the prompt 407. The fifth instruction includes an instruction to present at least one proposed revision 313 for making the numerical constraint 311 conform to the specification if it is determined that the numerical constraint 311 does not conform to the specification. The fifth instruction can be, for example, "Generate a proposed revision for matching the range of the numerical constraint extracted from the document 303 with the range of the numerical constraint extracted from the document 301." The proposed revision 313 corresponds to the second proposed revision described above.

[0162] [Step S17] In step S17, the processing unit 130 causes the language model to generate a response sentence 507 from the prompt via the network 30. The response sentence 507 includes at least one revision suggestion 313. For example, as shown in FIG. 7D , the processing unit 130 transmits the prompt 407 to the language model 250, thereby generating a response sentence 507 in response to the prompt 407. The response sentence 507 corresponds to the fifth response sentence described above.

[0163] The proposed revision 313 may be, for example, a description of a numerical constraint generated by a language model. In the information processing method of this embodiment, the proposed revision 313 is a numerical constraint, and a proposed revision of the numerical constraint 311 corresponding to the component 304 will be described.

[0164] [Step S18] In step S18, the processing unit 130 generates result data 317 based on the components 304, the numerical limitations 310, the numerical limitations 311, and the proposed revision 313. Fig. 11B shows an example in which the generated result data 317 is output to the display unit of the information terminal 20. In the example shown in Fig. 11B, in addition to the determination result 207, the components 304, the numerical limitations 310, the numerical limitations 311, and the proposed revision 313 are displayed in a table format. The result data 317 corresponds to the third result data described above.

[0165] 11B , it is preferable to display only records for which the judgment result 207 is "FALSE." For example, if the number of records for which the judgment result 207 is "FALSE" is m (m is an integer between 0 and n), m revision proposals 313[1] to 313[m] are generated and displayed. It is preferable to highlight the parts of the numerical constraint 311 included in the revision proposal 313. For example, highlighting methods include changing the color of the text, increasing the text size, changing the font, making the text bold, underlining, and adding a background color.

[0166] As described above, a language model can be used to confirm suggested corrections to descriptions in a document. Furthermore, document proofreading using a language model can be supported. Note that the language model 230 and the language model 250 may be the same model or different models. For example, if the same model is used, the system can be simplified. Furthermore, if different models are used, the system can be made lighter and optimized. Specifically, by using BERT for the language model 230 that extracts descriptions from a document, the generation of a prompt in the processing unit 130 can be omitted.

[0167] <Configuration Example 2 of Information Processing System> Fig. 12 shows another example of the information processing system of this embodiment. The information processing system of this embodiment has an information processing device 11, an information processing device 15, an information terminal 20, and an information processing device 40. In the information processing system shown in Fig. 12, the information processing device 11 is connected to the information processing device 40 via a network 30. The information processing device 11 is also connected to the information processing device 15 and multiple information terminals 20 via a network 31. In Fig. 12, information terminals 20a and 20b are shown as examples of the information terminals 20.

[0168] 12 is mainly used to relay transmission and reception of data between the information terminal 20 and the information processing device 40. Then, in the information processing device 15, data DA2 is created using the data DA1.

[0169] First, the user inputs desired data DA1 into the information processing device 11 using the information terminal 20. The data DA1 is transmitted from the information terminal 20 to the information processing device 11 via the network 31.

[0170] Next, the information processing device 11 transmits the data DA1 to the information processing device 15 via the network 31.

[0171] Next, the information processing device 15 creates data DA2 using the data DA1. The information processing device 15 is configured to execute the various processes performed by the information processing device 10 described above.

[0172] Next, the information processing device 15 transmits the data DA2 to the information processing device 11 via the network 31.

[0173] Next, the information processing device 11 transmits the data DA2 to the information processing device 40 via the network 30.

[0174] Next, the data DB1 is transmitted from the information processing device 40 to the information processing device 11 via the network 30. The data DB1 is text data equivalent to a response sentence corresponding to the data DA2 input to the information processing device 40.

[0175] Next, the information processing device 11 transmits the data DB2 to the information terminal 20 via the network 31. The data DB2 is data based on the data DB1 input to the information processing device 11. As a result, the user can obtain the data DB2, which is the data DA1 updated based on the data DB1.

[0176] The data DB2 can be created by the information processing device 11 or the information processing device 15. For example, the information processing device 11 may input the data DB1 input from the information processing device 40 to the information processing device 15. Then, the information processing device 15 may create the data DB2 based on the data DB1.

[0177] The information processing system shown in FIG. 12, like the information processing system shown in FIG. 1, is suitable for a case where a user who uses information terminal 20 and a service provider belong to the same organization such as a company.

[0178] For example, it is preferable that data be transmitted and received between the information terminal 20 and the information processing device 11 using a network 31 established within an organization such as a company. It is also preferable that data be transmitted and received between the information processing device 15 and the information processing device 11 using a network 31 established within an organization such as a company. It is also preferable that data be transmitted and received between the information processing device 11 and the information processing device 40 using the Internet. This allows for more secure use of applications, tools, services, etc. provided outside the organization than when the information terminal 20 is directly connected to the information processing device 40 via the Internet. However, connecting the information processing device 15 to the Internet may raise the risk of external cyberattacks, etc. The information processing system shown in FIG. 12 is preferable from a security perspective because it does not require the information processing device 15 to be directly connected to the information processing device 40 via the Internet.

[0179] Fig. 13 is a block diagram of the information processing system shown in Fig. 12. In Fig. 13, an example of the configuration of the information processing device 11 and the information processing device 15 will be mainly described.

[0180] The information processing device 11 includes a receiving unit 110 , a storage unit 120 , a processing unit 130 , an output unit 140 , and a transmission path 150 .

[0181] For the reception unit 110, storage unit 120, output unit 140, and transmission path 150 of the information processing device 11, the descriptions of the information processing device 10 can be referred to. The following mainly describes the differences from the information processing device 10.

[0182] The information processing device 15 includes a receiving unit 115 , a storage unit 125 , a processing unit 135 , an output unit 145 , and a transmission path 155 .

[0183] The receiving unit 110 receives data from the output unit 145 via the network 31b.

[0184] The receiving unit 115 receives data from the output unit 140 via the network 31a.

[0185] The information supplied to the reception unit 115 is supplied to one or both of the storage unit 125 and the processing unit 135 via the transmission path 155 .

[0186] The storage unit 125 has a function of storing a program executed by the processing unit 135. The storage unit 125 may also have a function of storing data created by the processing unit 135 (e.g., calculation results, analysis results, inference results), data input to the reception unit 115, etc. The storage unit 125 may have various configurations applicable to the storage unit 120.

[0187] The processing unit 135 has a function of performing processes such as calculation, analysis, and inference using data supplied from one or both of the reception unit 115 and the storage unit 125. The processing unit 135 can supply the created data (e.g., calculation results, analysis results, and inference results) to one or both of the storage unit 125 and the output unit 145. The processing unit 135 can use various configurations applicable to the processing unit 130.

[0188] The processing unit 135 has a function of acquiring data from the storage unit 125 .

[0189] The processing unit 135 extracts blocks contained in the target sentence and creates an instruction sentence, etc., using the data received by the receiving unit 115. The processing unit 135 also creates a prompt based on the target sentence and the instruction sentence.

[0190] The output unit 140 outputs the data to the reception unit 115 via the network 31a.

[0191] The output unit 145 outputs information based on the processing result of the processing unit 135. The output unit 145 can supply at least one of the calculation result, analysis result, and inference result of the processing unit 135 to an external device of the information processing device 15.

[0192] The output unit 145 outputs the data to the reception unit 110 of the information processing device 11 via the network 31b.

[0193] The transmission path 155 has a function of transmitting data. Data can be transmitted and received between the reception unit 115, the storage unit 125, the processing unit 135, and the output unit 145 via the transmission path 155.

[0194] The processing section 130 and the processing section 135 can each include one or both of a transistor having a metal oxide in a channel formation region (OS transistor) and a transistor having silicon in a channel formation region (Si transistor).

[0195] <Configuration Example 3 of Information Processing System> Fig. 14 shows an example of an information processing system according to this embodiment. In the information processing system shown in Fig. 14, an information processing device 10 is connected to an information processing device 40 and a plurality of information terminals 20 via a network 30. In Fig. 14, the above-mentioned information terminals 20a to 20d are shown as examples of the information terminals 20.

[0196] The flow of data in the information processing system shown in FIG. 14 can be understood by referring to the description of FIG. 2 by replacing the network 31 with the network 30.

[0197] A user of the information processing system can access the information processing device 10 from an information terminal 20. The user can then receive a service using the information processing method according to one aspect of the present invention.

[0198] The information processing system shown in FIG. 14 is suitable for a case where a user who uses the information terminal 20 and a service provider belong to different organizations such as companies.

[0199] The information processing device 10 is connected to an information terminal 20 used by a user who receives a service via a network 30 (typically, the Internet). A service provider can provide the service using the information processing device 10. Data is also transmitted and received between the information processing device 10 and the information processing device 40 using the network 30 (typically, the Internet). This allows applications, tools, services, etc. using the information processing device 40 to be used more safely than when the information terminal 20 is directly connected to the information processing device 40 via the Internet.

[0200] <Configuration Example 4 of Information Processing System> Fig. 15 shows an example of an information processing system according to this embodiment. In the information processing system shown in Fig. 15, an information processing device 11 is connected to an information processing device 40 and a plurality of information terminals 20 via a network 30. In Fig. 15, the above-mentioned information terminals 20a to 20d are shown as examples of the information terminals 20. Furthermore, the information processing device 11 is connected to an information processing device 15 via a network 31.

[0201] A user of the information processing system can access the information processing device 11 from an information terminal 20. The user can then receive services using the information processing method according to one aspect of the present invention.

[0202] The information processing system shown in FIG. 15, like the information processing system shown in FIG. 14, is suitable for a case where a user who uses information terminal 20 and a service provider belong to different organizations such as companies.

[0203] The information processing device 11 is connected to an information terminal 20 used by a user receiving a service via the Internet. Preferably, data is transmitted and received between the information processing device 11 and the information processing device 15 using a network 31 established within an organization such as a company that provides the service. The service provider can provide the service using the information processing device 11 and the information processing device 15. Data is also transmitted and received between the information processing device 11 and the information processing device 40 using the Internet. This allows applications, tools, services, etc. using the information processing device 40 to be used more safely than when the information terminal 20 is directly connected to the information processing device 40 via the Internet. Furthermore, the information processing device 15 does not need to be directly connected to the information processing device 40 via the Internet, which is preferable from the perspective of security.

[0204] 1, data transmission and reception between the information processing device 10 and the information processing device 40 can also be performed using a network 31 established within an organization such as a company. In this case, either the network 30 or the network 31 can be applied to transmission and reception of data between the information terminal 20 used by a user and the information processing device 10.

[0205] According to one aspect of the present invention, it is possible to provide an information processing system or an information processing method that utilizes a language model to support document correction. According to one aspect of the present invention, it is possible to provide a highly convenient information processing system or an information processing method. According to one aspect of the present invention, it is possible to provide a novel information processing system or an information processing method.

[0206] A plurality of configuration examples shown in this embodiment can be combined as appropriate.

[0207] 10: Information processing device, 11: Information processing device, 15: Information processing device, 20: Information terminal, 20a: Information terminal, 20b: Information terminal, 20c: Information terminal, 20d: Information terminal, 21: Housing, 30: Network, 30a: Network, 30b: Network, 31: Network, 31a: Network, 31b: Network, 40: Information processing device, 110: Reception unit, 115: Reception unit, 120: Storage unit, 125: Storage unit, 130: Processing unit, 135: Processing unit ,140: Output unit, 145: Output unit, 150: Transmission path, 155: Transmission path, 201: Judgment, 203: Judgment result, 205: Judgment, 207: Judgment result, 210: Language model, 220: Language model, 225: Language model, 230: Language model, 250: Language model, 301: Document, 302[1]: Component, 302[2]: Component, 302[3]: Component, 302[4]: Component, 302[n]: Component, 302: Component, 303: Document, 304 [1]: Component, 304[2]: Component, 304[3]: Component, 304[n]: Component, 304: Component, 305[1]: Description, 305[2]: Description, 305[3]: Description, 305[4]: Description, 305[n]: Description, 305: Description, 306[1,1]: Specific example, 306[1,3]: Specific example, 306[1]: Specific example, 306[2,1]: Specific example, 306[2,5]: Specific example, 306[3,1]: Specific example, 306[3,2]: Specific example, 3 06[n,1]: Specific example, 306[n]: Specific example, 306: Specific example, 307[1]: Revision proposal, 307[2]: Revision proposal, 307[3]: Revision proposal, 307[4]: Revision proposal, 307[n]: Revision proposal, 307: Revision proposal, 308[1,1]: Example of revision, 308[1,2]: Example of revision, 308[1]: Example of revision, 308[3,1]: Example of revision, 308[3,3]: Example of revision, 308[4,1]: Example of revision, 308[4,5]: Example of revision, 308[n,1]: Example of revision, 308[n,4]: Example of addition, 308[n]: Example of addition, 308: Example of addition, 309[1]: Draft description, 309[2]: Draft description, 309[3]: Draft description, 309[4]: Draft description, 309[n]: Draft description, 309: Draft description, 310[1]: Numerical limitation, 310[2]: Numerical limitation, 310[3]: Numerical limitation, 310[n]: Numerical limitation, 310: Numerical limitation, 311[1]: Numerical limitation, 311[2]: Numerical limitation, 311[3]: Numerical limitation, 311[n]: Numerical limitation ,311: Numerical Limitation, 313[1]: Correction Suggestion, 313[m]: Correction Suggestion, 313: Correction Suggestion, 315: Result Data, 317: Result Data, 321: Edit Box, 323: Button, 325: Mouse Pointer, 327: Button, 401: Prompt, 403: Prompt, 404: Prompt, 405: Prompt, 407: Prompt, 501: Response Sentence, 503: Response Sentence, 504: Response Sentence, 505: Response Sentence, 507: Response Sentence,

Claims

A receiving unit, a processing unit, and an output unit, the receiving unit has a function of receiving document data including a first document and a second document; the output unit has a function of outputting result data, The processing unit extracting at least one component from the first document; creating a first prompt having a first directive including an instruction to extract at least one description corresponding to the component from the second document; causing a language model to generate a first response sentence from the first prompt; determining whether the description complies with a regulation; creating a second prompt having a second instructional text including an instruction to suggest a modification to bring the description into conformity with the specification if the description does not conform to the specification; and causing the language model to generate a second response sentence from the second prompt; generating the result data based on the components, the description, and the suggested modifications; An information processing system configured to execute the 　 In claim 1, The description includes at least one specific example corresponding to the component. 　 In claim 2, The condition that the description complies with the provision is that the number of specific examples included in the description reaches a prescribed number, the processing unit is configured to execute a process of creating a determination result including a value of the number of missing specific examples when the description does not conform to the rule, The second prompt includes the determination result. 　 In claim 3, The proposed revision includes the description and includes revised examples generated to match the number of specific examples that are lacking based on the determination. 　 A receiving unit, a processing unit, and an output unit, the receiving unit has a function of receiving document data including a first document and a second document; the output unit has a function of outputting result data, The processing unit A process of extracting at least one component and at least one first numerical limitation corresponding to the component from the first document; creating a first prompt having a first directive including an instruction to extract at least one second numerical limitation corresponding to the component from the second document; causing a language model to generate a first response sentence from the first prompt; a process of determining whether the second numerical limitation complies with a regulation; creating a second prompt having a second instructional sentence including an instruction to, if the second numerical limitation does not conform to the specification, present at least one suggested modification to make the second numerical limitation conform to the specification; causing the language model to generate a second response sentence from the second prompt; generating the result data based on the components, the second numerical limitations, and the proposed revision; An information processing system configured to execute the 　 In claim 5, The information processing system determines whether the second numerical limitation range matches the first numerical limitation range in the determination. 　 In any one of claims 1 to 6, the first document is a claim belonging to a patent application; An information processing system, wherein the second document is a specification belonging to the patent application.

Images